v0.6.8

janhq/janv0.6.8Aug 14, 2025by github-actions[bot]

AI Summary

Focuses on migrating documentation to Astro v2, improving llama.cpp argument handling and device parsing, and introducing per-model jinja template customization.

Key Highlights

  • Docs v2 Astro migration.
  • Improved llama.cpp argument handling and device parsing tests.
  • Per-model jinja template customization.
  • Support for AVX2 instruction support on MacOS Intel CPUs.

New Features

  • Docs v2 Astro migration
  • Improve llama.cpp argument handling and add device parsing tests
  • Jinja template customize per model instead provider level
  • Add support for overriding tensor buffer type

Full Release Notes

## What's Changed
* Sync Release/v0.6.6 into dev by @louis-menlo in https://github.com/menloresearch/jan/pull/5973
* fix: thread sorting issue by @cmppoon in https://github.com/menloresearch/jan/pull/5976
* ✨enhancement: blurry logo model provider by @urmauur in https://github.com/menloresearch/jan/pull/5986
* fix: missing text color responsive left panel by @urmauur in https://github.com/menloresearch/jan/pull/5989
* fix assistant dropdown onClick not triggered consistently by @cmppoon in https://github.com/menloresearch/jan/pull/5991
* Sync Release/v0.6.6 into dev by @louis-menlo in https://github.com/menloresearch/jan/pull/5997
* Add comprehensive Products section and reorganize documentation structure by @ramonpzg in https://github.com/menloresearch/jan/pull/5958
* Sync release/v0.6.6 into dev by @louis-menlo in https://github.com/menloresearch/jan/pull/6004
* refactor: clean up cortex by @louis-menlo in https://github.com/menloresearch/jan/pull/6003
* ci: enable PR trigger for dev branch in tauri nightly workflow by @Minh141120 in https://github.com/menloresearch/jan/pull/6014
* fix: react state loop from hooks useMediaQuery by @urmauur in https://github.com/menloresearch/jan/pull/6031
* fix: wrong desc setting cont_batching by @urmauur in https://github.com/menloresearch/jan/pull/6034
* Fix: Llama.cpp server hangs on model load by @qnixsynapse in https://github.com/menloresearch/jan/pull/6030
* feat(docs): Docs v2 Astro migration by @ramonpzg in https://github.com/menloresearch/jan/pull/5950
* feat: Improve llama.cpp argument handling and add device parsing tests by @qnixsynapse in https://github.com/menloresearch/jan/pull/6041
* fix: show error toast message on download error by @cmppoon in https://github.com/menloresearch/jan/pull/6044
* fix: Generate A Response button does not show context size error dialog by @urmauur in https://github.com/menloresearch/jan/pull/6029
* fix connected servers status not in sync when edit mcp json by @cmppoon in https://github.com/menloresearch/jan/pull/6020
* feat: Add check for AVX2 instruction support for MCP on MacOS with Intel CPUs by @shmutalov in https://github.com/menloresearch/jan/pull/5530
* chore: skip nightly build workflow for external contributor by @Minh141120 in https://github.com/menloresearch/jan/pull/6050
* fix: support missing llamacpp cuda backends by @louis-menlo in https://github.com/menloresearch/jan/pull/6046
* ci: disable autoqa on nightly build by @Minh141120 in https://github.com/menloresearch/jan/pull/6051
* ✨feat: recommended label llamacpp setting by @urmauur in https://github.com/menloresearch/jan/pull/6052
* Fix: Improve Llama.cpp model path handling and error handling by @qnixsynapse in https://github.com/menloresearch/jan/pull/6045
* ✨feat: jinja template customize per model instead provider level by @urmauur in https://github.com/menloresearch/jan/pull/6053
* fix: Jan hub model detail and deep link by @louis-menlo in https://github.com/menloresearch/jan/pull/6024
* fix: Add conditional Vulkan support check for better GPU compatibility by @qnixsynapse in https://github.com/menloresearch/jan/pull/6066
* Readme Update and Additional Model Providers by @ramonpzg in https://github.com/menloresearch/jan/pull/6064
* fix: gpt-oss thinking block by @urmauur in https://github.com/menloresearch/jan/pull/6071
* fix: should not include reasoning text in the chat completion request by @louis-menlo in https://github.com/menloresearch/jan/pull/6072
* chore: update workflow name by @Minh141120 in https://github.com/menloresearch/jan/pull/6073
* ci: deprecate jan docs new release workflow in favor of jan-docs by @Minh141120 in https://github.com/menloresearch/jan/pull/6078
* Add gpt-oss local installation blog post by @eckartal in https://github.com/menloresearch/jan/pull/6075
* feat: Add support for overriding tensor buffer type by @qnixsynapse in https://github.com/menloresearch/jan/pull/6062
* refactor: move session management & port allocation to backend by @qnixsynapse in https://github.com/menloresearch/jan/pull/6083
* 🐛fix: onboarding loop by @urmauur in https://github.com/menloresearch/jan/pull/6054
* refactor: Use more precise terminology in API server logs by @qnixsynapse in https://github.com/menloresearch/jan/pull/6085
* fix: update ux recemmend backend label into desc setting by @urmauur in https://github.com/menloresearch/jan/pull/6088
* feat: Introduce structured error handling for llamacpp extension by @qnixsynapse in https://github.com/menloresearch/jan/pull/6087
* refactor: clean up unused hardware apis by @louis-menlo in https://github.com/menloresearch/jan/pull/6089
* added v0.6.7 changelog and jupyter mcp tutorial by @ramonpzg in https://github.com/menloresearch/jan/pull/6116
* fix: Prevent accidental message submitting on ChatInput for IME users by @B0sh in https://github.com/menloresearch/jan/pull/6109
* adding handbook, blog, and changelog to jan docs v2 by @ramonpzg in https://github.com/menloresearch/jan/pull/6118
* fix: bring back gpu detection - app data relocate issue by @louis-menlo in https://github.com/menloresearch/jan/pull/6119
* ci: update generate release note and jan docs release by @Minh141120 in https://github.com/menloresearch/jan/pull/6121
* docs: Update 3-epic.md by @freelerobot in https://github.com/menloresearch/jan/pull/6124
* docs: Update 4-goal.md by @freelerobot in https://github.com/menloresearch/jan/pull/6125
* ci: add path for tauri nightly build by @Minh141120 in https://github.com/menloresearch/jan/pull/6130
* fix: HF token is not used while searching repositories by @louis-menlo in https://github.com/menloresearch/jan/pull/6137
* fix: factory reset process got blocked by @louis-menlo in https://github.com/menloresearch/jan/pull/6140
* fix: visualize readme content for private repo with HF token by @louis-menlo in https://github.com/menloresearch/jan/pull/6141
* fix: Improve error message for invalid version/backend format by @qnixsynapse in https://github.com/menloresearch/jan/pull/6149
* fix: migrations model setting by @urmauur in https://github.com/menloresearch/jan/pull/6165
* fix: handle modelId special char by @urmauur  and @louis-menlo on https://github.com/menloresearch/jan/pull/6172
* fix: feature toggle auto updater by @Minh141120 and @louis-menlo on https://github.com/menloresearch/jan/pull/6175


## New Contributors
* @cmppoon made their first contribution in https://github.com/menloresearch/jan/pull/5976
* @shmutalov made their first contribution in https://github.com/menloresearch/jan/pull/5530
* @B0sh made their first contribution in https://github.com/menloresearch/jan/pull/6109

**Full Changelog**: https://github.com/menloresearch/jan/compare/v0.6.6...v0.6.8